{"id":"W2098347799","doi":"10.1002/smr.416","title":"Near‐miss function clones in open source software: an empirical study","year":2009,"lang":"en","type":"article","venue":"Journal of Software Maintenance and Evolution Research and Practice","topic":"Software Engineering Research","field":"Computer Science","cited_by":86,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University; University of Saskatchewan","funders":"","keywords":"clone (Java method); Cloning (programming); Source code; Java; Computer science; Open source; Linux kernel; Benchmark (surveying); Operating system; Function (biology); Software maintenance; Software; Software system; Programming language; Biology; Genetics; Gene","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.01294318,0.0001723903,0.0003259854,0.0005083522,0.0004429923,0.001227644,0.001044176,0.0001137743,0.000006807976],"category_scores_gemma":[0.02604646,0.0001428812,0.00003449691,0.001291921,0.0001657103,0.004955716,0.00051042,0.001311692,0.00000827789],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002244648,"about_ca_system_score_gemma":0.0004945638,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002808802,"about_ca_topic_score_gemma":0.00003723095,"domain_scores_codex":[0.9959596,0.001239839,0.000514567,0.0004748903,0.001160534,0.0006505522],"domain_scores_gemma":[0.9923923,0.005105047,0.0002056458,0.0004433269,0.001408226,0.0004454437],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.006133824,0.003590057,0.7117676,0.00007327062,0.0001106637,0.001066339,0.005737573,0.001207293,0.0001485674,0.0009216238,0.01443383,0.2548094],"study_design_scores_gemma":[0.002250167,0.008973154,0.9571797,0.0001474563,0.00001302327,0.001253233,0.00246354,0.002121476,0.000005893241,0.009305771,0.01603782,0.0002487513],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4770942,0.001589106,0.5136427,0.006836171,0.0001825527,0.0005312452,0.000001108961,0.00007930504,0.00004353476],"genre_scores_gemma":[0.9483514,0.0002963695,0.05070065,0.0002934011,0.0001232912,0.00001178691,7.001218e-7,0.00001434454,0.0002080283],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4712572,"threshold_uncertainty_score":0.9998092,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06872976237691421,"score_gpt":0.4022159840448877,"score_spread":0.3334862216679735,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}